© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121687
    Prev
    Next
    INDEX
    Explanations

    tangent plane, tent cities, tenant farming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kaltura
    0.61
    aun
    0.60
     Eurostile
    0.57
    匈
    0.54
     אות
    0.53
     wodurch
    0.53
     avenue
    0.53
     tampil
    0.52
     MODKEY
    0.52
     (&
    0.52
    POSITIVE LOGITS
    ра
    0.69
    consumption
    0.68
    თან
    0.65
    텐
    0.65
    ми
    0.64
    و
    0.62
    、
    0.62
    ،
    0.62
    ව
    0.62
    Continuous
    0.61
    Activations Density 0.000%

    No Known Activations